Integrating GraphQL with AI
summary
Prototype converts plain English into GraphQL by using OpenAI Codex via the OpenAI completions endpoint and a Python pipeline, generates a query file, posts it to the Open Targets GraphQL API, and returns parsed JSON. Example: it reliably pulls p53 — top five diseases from Open Targets, produces repeatable, sourceable results (temperature low for consistency), and the repo contains runnable code showing the end-to-end conversion and queries.
AI-written summary · about
chapters (9)
- 0:00Introduction and welcome
- 1:48What is artificial intelligence
- 6:02Large language models explained
- 10:18Project motivation and risks
- 12:10Building the GraphQL AI integration
- 16:08Demo of the working system
- 17:57Benefits and credibility of the approach
- 20:28Future use cases and opportunities
- 22:35Q&A and contact information
related talks
29mClosing the Loop: How GraphQL Gives Coding Agents Eyes on What Actually Matters
14mKeynote: GraphQL in the AI Era
51mOpenAI and the AI that may overtake humans
30mGraphQL Field Discovery & Query Generation with Generative AI
01h 00mWorkshop: Getting Data Ready for AI - With Unified GraphQL &SQL Endpoints
01h 12mChatGPT and OpenAI API solutions: 👑 My Favourite Implementations
35mDynamic, Safe Ops Using AI to Generate Trusted Operations from Text Prompts
27mHow GraphQL Gives Coding Agents Eyes on What Actually Matters